Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/moru-ai/moru/claude-mdgit clone --depth 1 https://github.com/moru-ai/moruWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/moru-ai/moru/claude-md)<a href="https://agentmods.dev/instructions/moru-ai/moru/claude-md"><img src="https://agentmods.dev/badge/instructions/moru-ai/moru/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02147 | $0.02147 |
| Opus 5 | $0.01073 | $0.01073 |
| Sonnet 5 | $0.00429 | $0.00429 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
moru CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to moru AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moru SDKs
This repository contains all Moru SDKs (JS, Python, CLI) managed as a pnpm workspace.
Version Management with Changesets
We use Changesets for automated version management and releases.
Core Principle: Flexible
You just need changesets before releasing. Commit freely during development, and add changesets when you're ready to release.
When Changesets Are Needed
The following changes require changesets when included in a release:
- ✅ Features: New functionality
- ✅ Bug Fixes: Bug corrections
- ✅ Breaking Changes: Changes that break API compatibility
- ✅ Performance: Performance improvements
- ✅ Dependencies: Dependency updates affecting users
When Changesets Are NOT Needed
Skip changesets for:
- ❌ Documentation-only changes (README, comments)
- ❌ Test-only changes
- ❌ CI/CD configuration changes
- ❌ Internal tooling changes
Workflow (Flexible Approach)
Approach 1: Add as you develop (Recommended - won't forget)
# 1. Make code changes
git add <files>
git commit -m "feat: add new feature X"
# 2. Add changeset
pnpm changeset
# - Which packages? (select with spacebar)
# - Version type? (patch/minor/major)
# - Summary? (description for CHANGELOG)
git add .changeset/
git commit -m "chore: add changeset"
git push
Approach 2: Add later (More flexible)
# 1. Commit multiple changes freely
git commit -m "feat: add feature A"
git commit -m "fix: bug B"
git commit -m "feat: add feature C"
git push
# 2. Add changeset before release
git log --oneline -10 # Review recent changes
pnpm changeset # "Add features A and C, fix bug B"
git add .changeset/
git commit -m "chore: add changeset for v0.3.3"
git push
Either approach works. Choose what fits your team/personal preference.
Choosing the Right Version Type
Follow Semantic Versioning:
patch (0.3.1 → 0.3.2)
- Bug fixes with no API changes
- Performance improvements
- Internal refactoring
- Documentation updates affecting functionality
- Dependency patches
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 355 lines · 2,147 tokens per session scan A e7e309c3e478
moru CLAUDE.md is an instructions file published in the GitHub repository moru-ai/moru (78 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 2,147 tokens to every session, about $0.0107 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to moru AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
ship CLAUDE.md
Claude Code instructions for shipstatic/ship, covering claude.md, architecture, quick reference, key files and comments state the law; this file keeps the story.
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
ai-usagebar CLAUDE.md
Claude Code instructions for akitaonrails/ai-usagebar, covering claude.md, release checklist — must do all of these, hard invariants — never break these, secret-discipline rules (learned the hard way) and live api smoke discipline.
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.